Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3692 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4742. Min Act: -0.0001

Data Index: 1185712 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4375. Min Act: -0.0001

Data Index: 848148 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4144. Min Act: -0.0001

Data Index: 124917 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4124. Min Act: -0.0001

Data Index: 908947 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4238. Min Act: -0.0001

Data Index: 784011 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4085. Min Act: -0.0001

Data Index: 94766 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4016. Min Act: -0.0001

Data Index: 352840 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3943. Min Act: -0.0001

Data Index: 98744 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3939. Min Act: -0.0001

Data Index: 346982 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1048103 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.4099. Min Act: -0.0001

Data Index: 874950 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3963. Min Act: -0.0001

Data Index: 862080 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3703. Min Act: -0.0001

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3806. Min Act: -0.0001

Data Index: 917905 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3669. Min Act: -0.0001

Data Index: 727915 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3667. Min Act: -0.0001

Data Index: 747326 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3762. Min Act: -0.0001

Data Index: 513262 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3782. Min Act: -0.0001

Data Index: 1055153 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3741. Min Act: -0.0001

Data Index: 304429 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.4742. Min Range: -0.4742

Max Act: 0.3473. Min Act: -0.0001

Data Index: 142699 (C4 (Web Text))

Max Activating Token Index: 124